© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95118
    Prev
    Next
    INDEX
    Explanations

    Code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Legenda
    -0.45
    PONENTS
    -0.42
    
    -0.40
    corpion
    -0.39
    pytest
    -0.38
     tutela
    -0.38
    gebracht
    -0.36
    ::::::::
    -0.36
    IComponent
    -0.36
    MenuInflater
    -0.35
    POSITIVE LOGITS
     ویکی‌پدیای
    0.90
    SequentialGroup
    0.82
    \{\\
    0.69
     kaarangay
    0.69
    ulx
    0.68
     betweenstory
    0.66
    دانشنامهٔ
    0.66
    StructEnd
    0.66
    DataAnnotations
    0.65
    ברס
    0.65
    Activations Density 0.002%

    No Known Activations